AI model catalog
The best models for video, images and music. One balance for everything.
from 5 crFlux 2 ProPhotorealistic images from text or edit your photos (up to 8) - 1K/2K
from 6 crGPT Image 2Image generation and editing from a prompt
from 6 crGPT Image 2.5Image generation and editing from a prompt, up to 4K. Flare is faster, Sunburst is more precise
from 8 crNano Banana 2Google Gemini 3.1 Flash: fast image generation and editing, accurate text, up to 4K
from 18 crNano Banana ProGoogle DeepMind imaging: sharp 2K/4K, accurate text and character consistency
4 crNano Banana 2 LiteGoogle DeepMind: fast 1K images and photo editing - the cheapest option in the catalog
from 12 crSunoMusic tracks (vocals and instrumental) or sound effects from a prompt - powered by Suno V6
from 44 crGrok ImagineTurn a photo into realistic video with synced audio - xAI Grok, up to 15s
from 40 crWan 3.0Alibaba flagship video: up to 30 seconds with audio, photo and audio references, 480P-1080P
from 5 crWan 2.7 ImageImage generation and editing: Standard (1K/2K) or Pro (up to 4K) - Alibaba Wan 2.7
from 32 crWan 2.7Video from text, key frames or audio - 720p/1080p, up to 15s
6 crSeedream 5 LiteUp to 3K images from text or edit your photo - ByteDance Seedream 5
from 7 crSeedream 5 ProByteDance: precise photo editing, readable in-image text and lifelike portraits - 1K/2K
from 42 crKling 3.0Video from text and images with native audio, or transfer motion from a video (Motion)
from 33 crKling 2.6Video from text or your photo, or transfer motion from a video onto a character (Motion)
from 30 crHailuo 2.3Animate a photo into video: Standard or Pro quality - 6-10s, 768P/1080P
from 32 crHailuo 03MiniMax H3: text and frame driven video up to 2K with native audio - up to 15s
from 62 crSeedance 2.0ByteDance video from photo, video and audio references: Standard (up to 1080p) or quick Fast
from 140 crSeedance 2.5Up to 30 seconds: ByteDance next gen - multimodal references and precise local edits
from 38 crSeedance 2.0 MiniByteDance's cost-efficient video model: same family, lower price - 480p/720p up to 15s
from 20 crPixVerse V6Cinematic video from text or a photo, with native audio - up to 15s, up to 1080p
from 63 crGemini Omni VideoGoogle's multimodal video: generate from text and photos, with audio, up to 4K
from 7 crQwen Image 3.0 ProAlibaba imaging: realistic output, clean in-image typography and photo editing - 1K/2K
from 84 crHappyHorseVideo from a text prompt or your photo - 720p/1080p, up to 15s
from 168 crHappyHorse Video EditEdit existing footage with a prompt: swap objects and restyle while keeping motion